
Ali Diab
@alidiabsf
@collective CEO.
ID: 1863636709025648643
02-12-2024 17:30:20
36 Tweet
10 Followers
11 Following





I always found it puzzling how language models learn so much from next-token prediction, while video models learn so little from next frame prediction. Maybe it's because LLMs are actually brain scanners in disguise. Idle musings in my new blog post: sergeylevine.substack.com/p/language-mod…












